junhua024-chai-11-full-_99974

developer_uid: junhua024

submission_id: junhua024-chai-11-full-_99974_v2

model_name: junhua024-chai-11-full-_99974_v2

model_group: junhua024/chai_11_full_q

status: torndown

timestamp: 2025-07-20T11:52:02+00:00

num_battles: 11277

num_wins: 5131

celo_rating: 1243.6

family_friendly_score: 0.5988

family_friendly_standard_error: 0.006931645692041681

submission_type: basic

model_repo: junhua024/chai_11_full_qkv102_o106_ffn106_1925

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5928397280843243, 'latency_mean': 1.6866682064533234, 'latency_p50': 1.6911115646362305, 'latency_p90': 1.8731111764907837}, {'batch_size': 3, 'throughput': 1.0564805092548069, 'latency_mean': 2.827239362001419, 'latency_p50': 2.8105759620666504, 'latency_p90': 3.1397796154022215}, {'batch_size': 5, 'throughput': 1.2732093641999103, 'latency_mean': 3.9154794883728026, 'latency_p50': 3.874431848526001, 'latency_p90': 4.399543118476868}, {'batch_size': 6, 'throughput': 1.3277972044091164, 'latency_mean': 4.4936033523082735, 'latency_p50': 4.503929018974304, 'latency_p90': 4.95471088886261}, {'batch_size': 8, 'throughput': 1.3975998651843728, 'latency_mean': 5.67917085647583, 'latency_p50': 5.662914514541626, 'latency_p90': 6.359430742263794}, {'batch_size': 10, 'throughput': 1.4114461449621583, 'latency_mean': 7.030162283182144, 'latency_p50': 7.114213824272156, 'latency_p90': 7.8633220911026}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: junhua024-chai-11-full-_99974_v2

is_internal_developer: False

language_model: junhua024/chai_11_full_qkv102_o106_ffn106_1925

model_size: 13B

ranking_group: single

throughput_3p7s: 1.24

us_pacific_date: 2025-07-20

win_ratio: 0.4549968963376785

generation_params: {'temperature': 1.0, 'top_p': 0.88, 'min_p': 0.0, 'top_k': 10, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name junhua024-chai-11-full-99974-v2-mkmlizer
Waiting for job on junhua024-chai-11-full-99974-v2-mkmlizer to finish
junhua024-chai-11-full-99974-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
junhua024-chai-11-full-99974-v2-mkmlizer: ║                                                                     ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║                                                                     ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║  https://mk1.ai                                                     ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║                                                                     ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║  belonging to:                                                      ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║                                                                     ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║  Chai Research Corp.                                                ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
junhua024-chai-11-full-99974-v2-mkmlizer: ║                                                                     ║
junhua024-chai-11-full-99974-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
Failed to get response for submission mistralai-mistral-nem_93303_v522: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v522-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
junhua024-chai-11-full-99974-v2-mkmlizer: Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
Failed to get response for submission mistralai-mistral-nem_93303_v522: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v522-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission mistralai-mistral-nem_93303_v522: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v522-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
junhua024-chai-11-full-99974-v2-mkmlizer: quantized model in 42.162s
junhua024-chai-11-full-99974-v2-mkmlizer: Processed model junhua024/chai_11_full_qkv102_o106_ffn106_1925 in 170.266s
junhua024-chai-11-full-99974-v2-mkmlizer: creating bucket guanaco-mkml-models
junhua024-chai-11-full-99974-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
junhua024-chai-11-full-99974-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/junhua024-chai-11-full-99974-v2/nvidia
junhua024-chai-11-full-99974-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/junhua024-chai-11-full-99974-v2/nvidia/config.json
junhua024-chai-11-full-99974-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/junhua024-chai-11-full-99974-v2/nvidia/special_tokens_map.json
junhua024-chai-11-full-99974-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/junhua024-chai-11-full-99974-v2/nvidia/tokenizer_config.json
junhua024-chai-11-full-99974-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/junhua024-chai-11-full-99974-v2/nvidia/tokenizer.json
junhua024-chai-11-full-99974-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/junhua024-chai-11-full-99974-v2/nvidia/flywheel_model.0.safetensors
Job junhua024-chai-11-full-99974-v2-mkmlizer completed after 201.26s with status: succeeded
Stopping job with name junhua024-chai-11-full-99974-v2-mkmlizer
Pipeline stage MKMLizer completed in 201.75s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service junhua024-chai-11-full-99974-v2
Waiting for inference service junhua024-chai-11-full-99974-v2 to be ready
Failed to get response for submission junhua024-chai-16-full-_96988_v4: ('http://junhua024-chai-16-full-96988-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:36884->127.0.0.1:8080: read: connection reset by peer\n')
Failed to get response for submission mistralai-mistral-nem_93303_v522: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v522-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission mistralai-mistral-nem_93303_v522: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v522-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission mistralai-mistral-nem_93303_v522: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v522-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission chaiml-nis-qwen32b-sim_98336_v34: HTTPConnectionPool(host='chaiml-nis-qwen32b-sim-98336-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission mistralai-mistral-nem_93303_v522: HTTPConnectionPool(host='mistralai-mistral-nem-93303-v522-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service junhua024-chai-11-full-99974-v2 ready after 332.40707659721375s
Pipeline stage MKMLDeployer completed in 332.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4322004318237305s
Received healthy response to inference request in 2.181288957595825s
Received healthy response to inference request in 1.9710609912872314s
Received healthy response to inference request in 1.9137229919433594s
Received healthy response to inference request in 1.7973718643188477s
5 requests
0 failed requests
5th percentile: 1.82064208984375
10th percentile: 1.8439123153686523
20th percentile: 1.890452766418457
30th percentile: 1.9251905918121337
40th percentile: 1.9481257915496826
50th percentile: 1.9710609912872314
60th percentile: 2.055152177810669
70th percentile: 2.1392433643341064
80th percentile: 2.2314712524414064
90th percentile: 2.3318358421325684
95th percentile: 2.3820181369781492
99th percentile: 2.422163972854614
mean time: 2.0591290473937987
Pipeline stage StressChecker completed in 11.88s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.72s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.75s
Shutdown handler de-registered
junhua024-chai-11-full-_99974_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5130.06s
Shutdown handler de-registered
junhua024-chai-11-full-_99974_v2 status is now inactive due to auto deactivation removed underperforming models
junhua024-chai-11-full-_99974_v2 status is now torndown due to DeploymentManager action